Application of Generalized Frequency Response Functions and Improved Convolutional Neural Network to Fault Diagnosis of Heavy-duty Industrial Robot

Abstract The combination of nonlinear spectrum and convolutional neural network (CNN) is efficient for fault diagnosis of nonlinear system. However, in traditional method, the nonlinear spectrum calculation was accomplished by identification algorithm outside the CNN, which reduced the diagnosis efficiency. To solve this problem, a novel CNN with the function of spectrum calculation and fault diagnosis is designed, in which the spectrum calculation network and the fault diagnosis network are connected in series. By extracting the optimized parameters of network, the nonlinear spectrum based on generalized frequency response function (GFRF) is obtained in the former network. Then, the GFRF spectrum is automatically put into the latter network for feature extraction and diagnosis. Hence, after determining the structure of the CNN, only by system input and output, the fault diagnosis can be realized, which avoids the complex process in traditional method. What's more, a new error cost function model is designed to guide the network parameters optimization in the direction of feature classification, which is conductive to improve the diagnosis accuracy. The proposed network model is applied to the heavy-duty industrial robot system, and the best performance is demonstrated by several experiments.

[1]  Haixia Hu,et al.  Design and kinematics analysis of the executing device of heavy-duty casting robot , 2020 .

[2]  Edward J. Powers,et al.  Optimal Volterra kernel estimation algorithms for a nonlinear communication system for PSK and QAM inputs , 2001, IEEE Trans. Signal Process..

[3]  Hui Wang,et al.  A New Intelligent Bearing Fault Diagnosis Method Using SDP Representation and SE-CNN , 2020, IEEE Transactions on Instrumentation and Measurement.

[4]  Haiyang Pan,et al.  Sigmoid-based refined composite multiscale fuzzy entropy and t-SNE based fault diagnosis approach for rolling bearing , 2018, Measurement.

[5]  Yang Kun,et al.  A new methodology for joint stiffness identification of heavy duty industrial robots with the counterbalancing system , 2018, Robotics and Computer-Integrated Manufacturing.

[6]  S. Billings,et al.  Recursive algorithm for computing the frequency response of a class of non-linear difference equation models , 1989 .

[7]  Yongchao Yang,et al.  CNN-LSTM deep learning architecture for computer vision-based modal frequency detection , 2020 .

[8]  Xingsheng Gu,et al.  Multi-block statistics local kernel principal component analysis algorithm and its application in nonlinear process fault detection , 2020, Neurocomputing.

[9]  Yi Qin,et al.  The Optimized Deep Belief Networks With Improved Logistic Sigmoid Units and Their Application in Fault Diagnosis for Planetary Gearboxes of Wind Turbines , 2019, IEEE Transactions on Industrial Electronics.

[10]  Dikai Liu,et al.  A comprehensive approach to real-time fault diagnosis during automatic grit-blasting operation by autonomous industrial robots , 2018 .

[11]  Jouni Mattila,et al.  Joint-Space Kinematic Model for Gravity-Referenced Joint Angle Estimation of Heavy-Duty Manipulators , 2017, IEEE Transactions on Instrumentation and Measurement.

[12]  Hanling Mao,et al.  The construction and comparison of damage detection index based on the nonlinear output frequency response function and experimental analysis , 2018, Journal of Sound and Vibration.

[13]  Jinrui Wang,et al.  A novel bearing intelligent fault diagnosis framework under time-varying working conditions using recurrent neural network. , 2019, ISA transactions.

[14]  Huan-Kun HSU,et al.  Intelligent Fault Detection, Diagnosis and Health Evaluation for Industrial Robots , 2021 .

[15]  S. Billings,et al.  Mapping non-linear integro-differential equations into the frequency domain , 1990 .

[16]  Xiangdong Wang,et al.  Multiscale local features learning based on BP neural network for rolling bearing intelligent fault diagnosis , 2020, Measurement.

[17]  Xining Zhang,et al.  Fault diagnosis of rolling bearing under fluctuating speed and variable load based on TCO Spectrum and Stacking Auto-encoder , 2019, Measurement.

[18]  Yunpeng Zhu,et al.  Design of Nonlinear Systems in the Frequency Domain: An Output Frequency Response Function-Based Approach , 2018, IEEE Transactions on Control Systems Technology.

[19]  Xiong Luo,et al.  Compliance Control Using Hydraulic Heavy-Duty Manipulator , 2019, IEEE Transactions on Industrial Informatics.

[20]  Zhuang Fu,et al.  Fault diagnosis for industrial robots based on a combined approach of manifold learning, treelet transform and Naive Bayes. , 2020, The Review of scientific instruments.

[21]  Robert X. Gao,et al.  Virtualization and deep recognition for system fault classification , 2017 .

[22]  Changan Zhu,et al.  A novel multi-adversarial cross-domain neural network for bearing fault diagnosis , 2021, Measurement Science and Technology.

[23]  Hui Ma,et al.  Feature extraction method based on NOFRFs and its application in faulty rotor system with slight misalignment , 2020 .

[24]  Weidong Li,et al.  Transfer learning enabled convolutional neural networks for estimating health state of cutting tools , 2021, Robotics Comput. Integr. Manuf..

[25]  Xu Han,et al.  A Moment Approach to Positioning Accuracy Reliability Analysis for Industrial Robots , 2020, IEEE Transactions on Reliability.

[26]  Youxian Sun,et al.  A novel fault diagnosis method based on optimal relevance vector machine , 2017, Neurocomputing.

[27]  Meiqin Liu,et al.  Stacked sparse autoencoder with PCA and SVM for data-based line trip fault diagnosis in power systems , 2019, Neural Computing and Applications.

[28]  Wenyu Yang,et al.  Inverse dynamic analysis and position error evaluation of the heavy-duty industrial robot with elastic joints: an efficient approach based on Lie group , 2018 .

[29]  Robert X. Gao,et al.  Ensemble sparse supervised model for bearing fault diagnosis in smart manufacturing , 2020, Robotics Comput. Integr. Manuf..

[30]  Wei Zhang,et al.  Multibranch and Multiscale CNN for Fault Diagnosis of Wheelset Bearings Under Strong Noise and Variable Load Condition , 2020, IEEE Transactions on Industrial Informatics.

[31]  Lerui Chen,et al.  A novel method of combining generalized frequency response function and convolutional neural network for complex system fault diagnosis , 2020, PloS one.

[32]  Feng Gao,et al.  Fault diagnosis for multivariable non-linear systems based on non-linear spectrum feature , 2017 .

[33]  Sahin Yildirim,et al.  Fault detection on robot manipulators using artificial neural networks , 2011 .

[34]  Xiaohan Chen,et al.  Bearing fault diagnosis base on multi-scale CNN and LSTM model , 2020, Journal of Intelligent Manufacturing.

[35]  Xiaoqi Wang,et al.  A novel method of combining nonlinear frequency spectrum and deep learning for complex system fault diagnosis , 2020 .

[36]  Xin Gao,et al.  Deep learning in bioinformatics. , 2019, Methods.

[37]  Nan Ma,et al.  Modeling and Experimental Validation of a Compliant Underactuated Parallel Kinematic Manipulator , 2020, IEEE/ASME Transactions on Mechatronics.

[38]  Byeng D. Youn,et al.  Phase-based time domain averaging (PTDA) for fault detection of a gearbox in an industrial robot using vibration signals , 2020 .

[39]  Bin Li,et al.  An Automatic Cost Learning Framework for Image Steganography Using Deep Reinforcement Learning , 2021, IEEE Transactions on Information Forensics and Security.

[40]  Zi-Qiang Lang,et al.  The effects of linear and nonlinear characteristic parameters on the output frequency responses of nonlinear systems: The associated output frequency response function , 2018, Autom..

[41]  Jianyu Long,et al.  Attitude data-based deep hybrid learning architecture for intelligent fault diagnosis of multi-joint industrial robots , 2020 .

[42]  Deokwoo Jung,et al.  High-Accuracy Unsupervised Fault Detection of Industrial Robots Using Current Signal Analysis , 2019, 2019 IEEE International Conference on Prognostics and Health Management (ICPHM).

[43]  Mark D. McDonnell,et al.  Diagnosing Convolutional Neural Networks using Their Spectral Response , 2018, 2018 Digital Image Computing: Techniques and Applications (DICTA).

[44]  John A. Armstrong,et al.  Fast Solar Image Classification Using Deep Learning and Its Importance for Automation in Solar Physics , 2019, Solar Physics.